用Mamba设计高效边缘检测器，兼顾全局与细粒度信息。
EDMB: Edge Detector with Mamba
- 结合Mamba与全局-局部架构，捕捉长距离依赖和细节特征。
- 在BSDS500上多粒度精度达0.851，无需多尺度测试或额外数据。
- 可扩展至单标签数据集，适合追求效率与精度的边缘检测应用。
基于Transformer的模型在边缘检测中取得显著进展，但计算成本过高。近期视觉Mamba展现出高效捕捉长程依赖的能力。受此启发，我们提出一种基于Mamba的新颖边缘检测器EDMB，可高效生成高质量多粒度边缘。EDMB采用全局-局部架构，兼顾全局信息与细粒度线索，后者在普通Mamba中常被忽略。我们设计新型解码器，通过融合全局与细粒度特征构建可学习高斯分布，并从分布中采样生成多粒度边缘。为使多粒度边缘适用于单标签数据，引入证据下界损失监督分布学习。在多标签数据集BSDS500上，EDMB实现单粒度ODS 0.837、多粒度ODS 0.851，无需多尺度测试或额外PASCAL-VOC数据。显著的是，EDMB可扩展至单标签数据集如NYUDv2和BIPED。源代码已公开于https://github.com/Li-yachuan/EDMB。
原文摘要 · Abstract (English)
Transformer-based models have made significant progress in edge detection, but their high computational cost is prohibitive. Recently, vision Mamba have shown excellent ability in efficiently capturing long-range dependencies. Drawing inspiration from this, we propose a novel edge detector with Mamba, termed EDMB, to efficiently generate high-quality multi-granularity edges. In EDMB, Mamba is combined with a global-local architecture, therefore it can focus on both global information and fine-grained cues. The fine-grained cues play a crucial role in edge detection, but are usually ignored by ordinary Mamba. We design a novel decoder to construct learnable Gaussian distributions by fusing global features and fine-grained features. And the multi-grained edges are generated by sampling from the distributions. In order to make multi-granularity edges applicable to single-label data, we introduce Evidence Lower Bound loss to supervise the learning of the distributions. On the multi-label dataset BSDS500, our proposed EDMB achieves competitive single-granularity ODS 0.837 and multi-granularity ODS 0.851 without multi-scale test or extra PASCAL-VOC data. Remarkably, EDMB can be extended to single-label datasets such as NYUDv2 and BIPED. The source code is available at https://github.com/Li-yachuan/EDMB.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。